mlsanityData to 7 Oct 2026

Combating Label Distribution Shift for Active Domain Adaptation

arXiv 2208.06604 ↗First posted 13 Aug 2022cs.LG cs.AI cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch between source and target in domain adaptation, we devise a method that addresses the issue for the first time in ADA. At its heart lies a novel sampling strategy, which seeks target data that best approximate the entire target distribution as well as being representative, diverse, and uncertain. The sampled target data are then used not only for supervised learning but also for matching label distributions of source and target domains, leading to remarkable performance improvement. On four public benchmarks, our method substantially outperforms existing methods in every adaptation scenario.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 36 of its 66 references that are in the map. First posted on arXiv 13 Aug 2022.

Builds on

36 of 66 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  5. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  7. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  8. 2019A Closer Look at Few-shot Classificationcited by 679
  9. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  10. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  11. 2015Optimal Transport for Domain Adaptationcited by 457
  12. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
24 more
  1. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  2. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 333
  3. 2019Variational Adversarial Active Learningcited by 284
  4. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
  5. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  6. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  7. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 212
  8. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  9. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  10. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
  11. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  12. 2014Domain-Adversarial Neural Networkscited by 78
  13. 2019Active Adversarial Domain Adaptationcited by 73
  14. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  15. 2021Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptationcited by 67
  16. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  17. 2020Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptationcited by 41
  18. 2019Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understandingcited by 40
  19. 2021ECACL: A Holistic Framework for Semi-Supervised Domain Adaptationcited by 31
  20. 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
  21. 2021Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillationcited by 23
  22. 2021S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptationcited by 19
  23. 2022Learning Distinctive Margin toward Active Domain Adaptationcited by 18
  24. 2021Discrepancy-Based Active Learning for Domain Adaptationcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 4; 2025: 4; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  2. 2023Active Learning for Semantic Segmentation with Multi-class Label Querycited by 9
  3. 2024Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptationcited by 9
  4. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
  5. 2022Local Context-Aware Active Domain Adaptationcited by 4
  6. 2025Unified modality separation: A vision-language framework for unsupervised domain adaptationcited by 4
  7. 2025Enhancing Cost Efficiency in Active Learning with Candidate Set Querycited by 3
  8. 2024Active Prompt Learning with Vision-Language Model Priorscited by 2
  9. 2024D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignmentcited by 1
  10. 2025A Smart-Glasses for Emergency Medical Services via Multimodal Multitask Learningcited by 1
  11. 2023Source-free Active Domain Adaptation for Diabetic Retinopathy Grading Based on Ultra-wide-field Fundus Imagecited by 0
  12. 2024Theory-inspired Label Shift Adaptation via Aligned Distribution Mixturecited by 0
2 more
  1. 2025Learning What is Worth Learning: Active and Sequential Domain Adaptation for Multi-modal Gross Tumor Volume Segmentationcited by 0
  2. 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalancecited by 0